Article
Biochemical Research Methods
Jilong Bian, Xi Zhang, Xiying Zhang, Dali Xu, Guohua Wang
Summary: Accurate and effective drug-target interaction (DTI) prediction is crucial in speeding up drug development and reducing costs. This study proposes a shared-weight-based MultiheadCrossAttention mechanism to improve the accuracy and efficiency of DTI prediction. Experimental results on six public drug-target datasets demonstrate the superiority of the proposed method over existing baselines.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Biochemical Research Methods
Alperen Dalkiran, Ahmet Atakan, Ahmet S. Rifaioglu, Maria J. Martin, Rengul Cetin Atalay, Aybar C. Acar, Tunca Dogan, Volkan Atalay
Summary: This study investigates the use of deep transfer learning for predicting drug-target interactions with scarce training data. The approach involves pre-training a deep neural network with a large generalized dataset and then retraining/fine-tuning it with a small specialized target dataset. The evaluation shows that transfer learning is advantageous for predicting interactions with understudied targets.
Article
Biochemical Research Methods
Yuni Zeng, Xiangru Chen, Dezhong Peng, Lijun Zhang, Haixiao Huang
Summary: The proposed multi-granularity encoding method and multi-scaled self-attention (SAN) model improve drug-target interaction (DTI) prediction by encoding the chemical textual information of drugs and targets and extracting their various local patterns, respectively.
BMC BIOINFORMATICS
(2022)
Article
Biochemical Research Methods
Siyuan Liu, Yusong Wang, Yifan Deng, Liang He, Bin Shao, Jian Yin, Nanning Zheng, Tie-Yan Liu, Tong Wang
Summary: This study proposes a novel approach called IGT that improves the prediction performance of active binding drugs in virtual screening. Compared to existing methods, IGT achieves better results in binding activity and binding pose prediction, and demonstrates superior generalization ability to unseen receptor proteins. Furthermore, IGT shows promising accuracy in drug screening against severe acute respiratory syndrome coronavirus 2.
BRIEFINGS IN BIOINFORMATICS
(2022)
Article
Biochemical Research Methods
Hongmei Wang, Fang Guo, Mengyan Du, Guishen Wang, Chen Cao
Summary: This study proposes a novel method for predicting the relationship between drugs and targets. By constructing different level relationships of drugs and targets, and using line graph to model drug-target interaction, a graph transformer network is utilized for predicting drug-target interaction.
BMC BIOINFORMATICS
(2022)
Article
Biochemical Research Methods
Qichang Zhao, Guihua Duan, Haochen Zhao, Kai Zheng, Yaohang Li, Jianxin Wang
Summary: Drug discovery and drug repurposing benefit from the application of deep learning in predicting drug-target interactions (DTIs). A novel model called GIFDTI is proposed to address the challenges of representing local chemical environments, encoding long-distance relationships, and modeling intermolecular interactions. Evaluation results demonstrate that GIFDTI outperforms state-of-the-art methods in DTI prediction. Case studies also validate the accuracy and cost-effectiveness of the model. The code for GIFDTI is available at https://github.com/zhaoqichang/GIFDTI.
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS
(2023)
Article
Biology
Jiayue Hu, Wang Yu, Chao Pang, Junru Jin, Nhat Truong Pham, Balachandran Manavalan, Leyi Wei
Summary: DrugormerDTI is a novel neural network architecture that predicts drug-target interactions by learning the relationship between molecule graphs and protein residues.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Chemistry, Physical
Ziduo Yang, Weihe Zhong, Lu Zhao, Calvin Yu-Chian Chen
Summary: In this study, a mutual learning mechanism was proposed to bridge the gap between drug and target encoders, enhancing the generalization and interpretation capability of DTI modeling. The method was evaluated using benchmark kinase data sets and compared to three baseline models, showing significant improvement in predictive performance in settings where training and test sets share only targets or drugs. The experimental results demonstrated the effectiveness of the proposed mutual learning approach.
JOURNAL OF PHYSICAL CHEMISTRY LETTERS
(2021)
Article
Biochemical Research Methods
Yanyi Chu, Aman Chandra Kaushik, Xiangeng Wang, Wei Wang, Yufang Zhang, Xiaoqi Shan, Dennis Russell Salahub, Yi Xiong, Dong-Qing Wei
Summary: Drug-target interactions are crucial in drug discovery, but existing prediction methods suffer from low precision and high false-positive rates. The proposed DTI-CDF model significantly outperforms traditional methods and accurately predicts new DTIs.
BRIEFINGS IN BIOINFORMATICS
(2021)
Article
Biochemical Research Methods
Jiajie Peng, Yuxian Wang, Jiaojiao Guan, Jingyi Li, Ruijiang Han, Jianye Hao, Zhongyu Wei, Xuequn Shang
Summary: This paper proposes an end-to-end learning framework based on heterogeneous graph convolutional networks for drug-target interactions (DTI) prediction, named end-to-end graph (EEG)-DTI. The framework learns the feature representations of drugs and targets during training, and outperforms existing methods in DTI prediction.
BRIEFINGS IN BIOINFORMATICS
(2021)
Article
Biochemical Research Methods
Oguz C. Binatli, Mehmet Gonen
Summary: In this paper, we propose a novel framework called MOKPE to efficiently model heterogeneous data, particularly in the context of drug discovery and drug-target interactions. Our model preserves drug-target interactions as well as drug-drug and target-target similarities by projecting them into a unified embedding space. Experimental results demonstrate that our approach outperforms previous similarity-based methods and is effective in predicting unknown drug-target interactions.
BMC BIOINFORMATICS
(2023)
Review
Biochemical Research Methods
Yuni Zeng, Xiangru Chen, Yujie Luo, Xuedong Li, Dezhong Peng
Summary: In this study, an end-to-end model with multiple attention blocks was proposed to predict the binding affinity scores of drug-target pairs. The model encodes correlations between atoms using a relation-aware self-attention block and models the interaction between drug and target representations using a multi-head attention block. Experimental results show that the proposed approach outperforms existing methods by benefiting from encoded correlation and extracted interaction information.
BRIEFINGS IN BIOINFORMATICS
(2021)
Article
Mathematical & Computational Biology
Sofia D'Souza, K. V. Prema, S. Balaji, Ronak Shah
Summary: Chemogenomics, or proteochemometrics, uses computational methods to predict drug-target interactions based on large-scale data. This study develops a deep learning CNN model using one-dimensional SMILES for drugs and protein binding pocket sequences as inputs to predict unknown ligand-target interactions. The proposed method outperforms shallow machine learning methods in terms of prediction accuracy and computational efficiency.
INTERDISCIPLINARY SCIENCES-COMPUTATIONAL LIFE SCIENCES
(2023)
Article
Pharmacology & Pharmacy
Jackson G. de Souza, Marcelo A. C. Fernandes, Raquel de Melo Barbosa
Summary: Drug discovery is a time-consuming and expensive process, and strategies such as drug repositioning and repurposing are employed to accelerate and reduce costs. The prediction of drug-target interactions is crucial in this process, and this paper presents a new DTI prediction model using a deep-learning approach based on convolutional neural networks and representing molecule and protein sequences as images.
Article
Biochemical Research Methods
Tri Minh Nguyen, Thin Nguyen, Truyen Tran
Summary: By incorporating interaction information from related tasks, the proposed method shows advantages in predicting drug-target interactions compared to other pre-training methods.
BRIEFINGS IN BIOINFORMATICS
(2022)